• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.66 no.9
• /
• pp.1431-1436
• /
• 2017

The high-speed railway of catenary system, supplies a stable electric power supply to the train by satisfying the special conditions between pantograph and trolley wire, which operates more than 250km/h mutually sliding and feeding electric lines. According to Korean Railway Standard KRS PW 0026-13 (R), the standard for the grip strength of the dropper clamp in conventional line is established, but the high-speed railway line is not yet. When the grip strength of the dropper clamp is detached from the catenary line of the high-speed railway line, various problems may occur, such as damage to the pantograph due to the collision and arcing. In this paper, it is expected to be used as a basic data for establishing the durability criteria of the high-speed railway dropper clamp by verifying the dropper clamp on the Gyeong-bu and Honam high-speed line.

• Journal of the Korean Society of Manufacturing Technology Engineers
• /
• v.19 no.5
• /
• pp.672-677
• /
• 2010

The goal of this study is to simplify the measurement process of the flat zone length produced by a flexible disk grinding system for the process automation. The image of workpiece in the grinding process is obtained, and the cutting speed and the feeding speed are controlled carefully to maximize the flat zone length. The gradient, the inflection point and the length of the line in the image are calculated, and the length is also measured by using a projector. Processing conditions and inversely proportional to flat zone length was changing. The flat zone length is estimated by Neural network algorithm considering the process conditions with the estimated error range as 0.06~3.61%, the Neural network algorithm for the grinding process estimation is found to be useful for building the process automation database.

• Journal of KIISE
• /
• v.44 no.7
• /
• pp.742-747
• /
• 2017

In this paper, we propose a novel approach to improve the performance of the Convolutional Neural Network(CNN) word embedding model on top of word2vec with the result of performing like doc2vec in conducting a document classification task. The Word Piece Model(WPM) is empirically proven to outperform other tokenization methods such as the phrase unit, a part-of-speech tagger with substantial experimental evidence (classification rate: 79.5%). Further, we conducted an experiment to classify ten categories of news articles written in Korean by feeding words and document vectors generated by an application of WPM to the baseline and the proposed model. From the results of the experiment, we report the model we proposed showed a higher classification rate (89.88%) than its counterpart model (86.89%), achieving a 22.80% improvement. Throughout this research, it is demonstrated that applying doc2vec in the document classification task yields more effective results because doc2vec generates similar document vector representation for documents belonging to the same category.

• The Korean Journal of Applied Statistics
• /
• v.32 no.6
• /
• pp.899-908
• /
• 2019

Massive in-depth neural networks with numerous parameters are powerful machine learning methods, but they have overfitting problems due to the excessive flexibility of the models. Dropout is one methods to overcome the problem of oversized neural networks. It is also an effective method that randomly drops input and hidden nodes from the neural network during training. Every sample is fed to a thinned network from an exponential number of different networks. In this study, instead of feeding one sample for each thinned network, two or more samples are used in fitting for one thinned network known as a Hybrid Dropout. Simulation results using real data show that the new method improves the stability of estimates and reduces the minimum error for the verification data.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.21 no.6
• /
• pp.660-669
• /
• 2010

In this paper, a multiple antenna system for next generation mobile applications is proposed. The proposed MIMO antenna consists of two parallel folded monopole antennas with the length of 100 mm and spacing of 6 mm and a decoupling network which locates at the top side of a mobile handset. In order to improve the isolation characteristic at the LTE band 13, a decoupling network was added between the two antenna elements placed close to each other. The decoupling network, consisting of two transmission lines, a shunt reactive component and common ground line, is simple and compact. To obtain the wide bandwidth characteristic, an wide folded patch structure generating the strong coupling between feeding and shorting lines through the slit is used at the bottom side of a mobile handset. Also, the performance of a multiple antenna system composed of three antenna elements is analyzed.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.48 no.7
• /
• pp.73-86
• /
• 2006

Concentrated poultry production in the State of Alabama, U.S.A. results in excessive poultry litter. Application of poultry litter to pastures and row crops serves as a cheap alternative to commercial fertilizer. However, over the years, poultry litter application to perennial forage crops in the Appalachian Plateau region of North Alabama has resulted in phosphorus (P) buildup in soils. Phosphorus index (P-index) and comprehensive nutrient management plans (CNMP) are often used as a best management practice (BMP) for proper land application of litter. Because nutrient management planning is often not done for small animal feeding operations (AFOs), and also because, in case of excess litter, litter transportation infrastructure has not been developed, over application of poultry litter to near by area is a common practice. To alleviate this problem, optimal poultry litter management and transportation infrastructure needs to be developed. This paper presents a methodology to optimize poultry litter application and transportation through efficient nutrient management planning and transportation network analysis. The goal was accomplished through implementation of three important modules, a P-Index module, a CNMP module, and a transportation network analysis module within ArcGIS, a Geographic Information System (GIS). The CNMP and P-Index modules assist with land application of poultry litter at a rate that is protective of water quality, while the transportation network analysis module helps transport excess litter to areas requiring litter in the Appalachian Plateau and Black Belt (a nutrient-deficient area) regions. Once fully developed and implemented, such a system will help alleviate water quality problems in the Appalachian Plateau region and poor soil fertility problems in the Black Belt region by optimizing land application and transportation. The utility of the methodology is illustrated through a hypothetical case study.

• The Journal of Korean Academic Society of Nursing Education
• /
• v.27 no.2
• /
• pp.175-185
• /
• 2021

Purpose: The aim of this study was to identify core keywords and topic groups in the 'Gestational diabetes mellitus (GDM) and Breastfeeding' field of research for better understanding research trends in the past 20 years. Methods: This was a text-mining and topic modeling study composed of four steps: 1) collecting abstracts, 2) extracting and cleaning semantic morphemes, 3) building a co-occurrence matrix, and 4) analyzing network features and clustering topic groups. Results: A total of 635 papers published between 2001 and 2020 were found in databases (Web of Science, CINAHL, RISS, DBPIA, RISS, KISS). Among them, 3,639 words extracted from 366 articles selected according to the conditions were analyzed by text network analysis and topic modeling. The most important keywords were 'exposure', 'fetus', 'hypoglycemia', 'prevention' and 'program'. Six topic groups were identified through topic modeling. The main topics of the study were 'cardiovascular disease' and 'obesity'. Through the topic modeling analysis, six themes were derived: 'cardiovascular disease', 'obesity', 'complication prevention strategy', 'support of breastfeeding', 'educational program' and 'management of GDM'. Conclusion: This study showed that over the past 20 years many studies have been conducted on complications such as cardiovascular diseases and obesity related to gestational diabetes and breastfeeding. In order to prevent complications of gestational diabetes and promote breastfeeding, various nursing interventions, including gestational diabetes management and educational programs for GDM pregnancies, should be developed in nursing fields.

• Journal of the Korean Society of Manufacturing Technology Engineers
• /
• v.22 no.3
• /
• pp.402-407
• /
• 2013

In this paper, the image processing for flexible disk grinding and the effect of the grinding conditions on the flat zone length of a workpiece are investigated, with the purpose of automating the grinding process. To accomplish this, three issues should be carefully studied. The first is finding the relationship between the flat zone length and the grinding conditions such as the cutting speed and feeding speed. The second is developing a neural network algorithm to predict the flat zone. The third is developing an image processing algorithm to measure the flat zone length of a workpiece. Slope analysis is used to determine straight and curved sections during the image processing. For verification, the estimated length and the length from the image processing are compared with the length measured by a projector. There is a minimum difference of 1.7% between the predicted and measured values. The results of this paper will be useful in compiling a database for process automation.

• The Journal of the Korea Contents Association
• /
• v.11 no.6
• /
• pp.42-50
• /
• 2011

This paper is to propose design and implementation methods of a pet dog management system that can effectively manage the pet dog in home through client such as a mobile terminal or a PC from remote location, in the absence of the owner in the house. Through this system, we can manage the dog efficiently via a series of monitoring and control functionalities of the dog such as observing of the dog's status, or feeding the dog, or taking the necessary measures on maintaining a healthy environment such as temperature/humidity sensing and turn on/off fans and lights, or sending SMS text to the owner from detection of the barking of the dog.

• Journal of the Korea Society of Computer and Information
• /
• v.23 no.11
• /
• pp.193-201
• /
• 2018

In this paper, we extracted relevant patent data and conducted statistical analysis to understand the technical development trend related to Wireless Power Transfer (WPT) for Light Rail Transit (LRT). Recently, with the development of WPT technologies, the Light Rail Transit (LRT) industry is concentrating on applying WPT to the power supply system of trains because of their advantages compared wired counterpart, such as low maintenance cost and high stability. This technology is divided into three areas: wireless feeding and collecting technology, high-frequency power converter technology and orbital and infrastructure technology. From each specific area, key words in patent document were extracted by TF-IDF method and analyzed by social network. In the keyword network, core word of each specific technology were extracted according to their degree centrality. Then, the multi-word phrases were also built to represent the concept of core technologies. Finally, based on the analysis results, the development strategies for each specifics technical area of WPT in LRT filed will be provided.